Kansei retrieval method using VPIC of traditional Japanese crafting objects

We propose Kansei retrieval method using the quantitative feature of traditional Japanese crafting object to provide a user with the desired presentation space in digital traditional Japanese crafting system. First, we extracted visual quantitative feature values by using visual pattern image coding (VPIC). Those values include the total number, the frequency, the dispersion rate and the deviation rate of variety for edge. Next, those quantitative feature values for traditional Japanese crafting objects are registered in the multimedia database. On the other hand, the relation between Kansei words and the visual feature of traditional Japanese crafting objects are analyzed by using the questionnaire. Last, the visual feature is related with the quantitative feature values. Through the above process, Kansei retrieval method can be realized. We describe the possibility of realization for Kansei retrieval method using the quantitative feature of 3D object.